Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "up_proj",
+    "v_proj",
     "down_proj",
     "gate_proj",
-    "q_proj",
-    "up_proj",
     "k_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6436bf1379ac6172d0e1d3cb7e6babe901481a0bf85f6511dc248091ae7b2564
+oid sha256:90695571950ad67a3e0254b360baf813110dbe8cff63c5e69fefaf0527feb126
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6a47a5aa38c949c525d632501a4798783ada4a754be36b9fba4a280af1c0a90
+oid sha256:6101dfc2f9cd7097d2109c91905cc43768db224f25dc6ff1eecf2fd5344e4d7c
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9673d22f265ed23c9ac8fe3534732259b5ca12d0692ce0ea4ceef5963b1b4fd
+oid sha256:12beed8359fe142c0bd78cf5e499f7058c2c13c901dc109a35a05e5a60f3c080
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012511729746637473,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.016265248670628715,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0012511729746637473,
       "eval_loss": 5.3348588943481445,
-      "eval_runtime": 21.7626,
-      "eval_samples_per_second": 15.485,
-      "eval_steps_per_second": 7.766,
+      "eval_runtime": 21.6661,
+      "eval_samples_per_second": 15.554,
+      "eval_steps_per_second": 7.8,
       "step": 1
+    },
+    {
+      "epoch": 0.006255864873318737,
+      "grad_norm": 2.4197850227355957,
+      "learning_rate": 5e-05,
+      "loss": 5.3435,
+      "step": 5
+    },
+    {
+      "epoch": 0.012511729746637473,
+      "grad_norm": 3.464526414871216,
+      "learning_rate": 0.0001,
+      "loss": 4.9746,
+      "step": 10
+    },
+    {
+      "epoch": 0.012511729746637473,
+      "eval_loss": 4.500220775604248,
+      "eval_runtime": 21.066,
+      "eval_samples_per_second": 15.997,
+      "eval_steps_per_second": 8.022,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 174263604609024.0,
+  "total_flos": 2265426859917312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead5b7fc61586b2958201c380a155c6aea1b2d68665b80146719865d15e5592b
+oid sha256:2cfbc4769ad26004d271be09fef8cbe6533227f2171a3427189a7c6b2a3ba35f
 size 6776